Basic Concepts in Skin Biopsy. Part I

Llamas‐Velasco, Mar; Paredes, Bruno E.

doi:10.1016/j.adengl.2011.05.005

Cited by 14 publications

(13 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The biopsy of cutaneous tissue samples is an invasive technique, common in dermatological practice and used in the diagnosis and analysis of changes in human skin structures and in the evaluation of therapeutic protocols used in integumentary system disorders. 1,14,32,40,41 HRUS emerged in 1970, as a noninvasive and nonionizing method to differentiate and measure skin layers, to identify skin lesions, and to monitor the evolution of dermatological treatments noninvasively, with high-quality images. [25][26][27][28][29][30][31][32]34,[36][37][38] Recent HRUS techniques using frequencies between 20 and 100 MHz are able to study the dermis and epidermis, to visualize the superficial structures of the integumentary system, and to identify dermal lesions.…”

Section: Discussionmentioning

confidence: 99%

Using high‐resolution ultrasound imaging to characterize dermal striae in human skin

Carvalho

Costa‐Júnior

Silva

et al. 2020

Skin Research and Technology

View full text Add to dashboard Cite

Dermal striae (DS) or stretch marks are a dermatological condition seen microscopically as the separation of collagen fibers and rupture of elastic fibers, which are curled and clumped at the edge of the lesion. 1 In this condition, fibrillin and elastin appear in reduced amounts and are reorganized in the deep dermis. The result is discontinuity of the dermal tissue and reduction in the thickness of the epidermis and papillary dermis. 1,2 Dermal striae are in the second layer of skin, the dermis. 1,3 It can occur in small or large quantities, elevated or depressed in aspect, and vary in shape and size. DS lesions tend to appear in a parallel formation and perpendicular to the skin tension lines (STL) 4,5 which are lines that determine the maximum tension direction of human skin. 6

show abstract

Section: Discussionmentioning

confidence: 99%

Using high‐resolution ultrasound imaging to characterize dermal striae in human skin

Carvalho

Costa‐Júnior

Silva

et al. 2020

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

“…On the other hand, since it performs per block wavelet transformation, blank blocks can be easily discarded so as to get more precise representations for irregular regions. We regard this feature extraction method potentially close to the intuition presented in many famous dermatology literatures [7][8] [9].…”

Section: B Region Feature Extractionmentioning

confidence: 98%

“…The second step is skin biopsy image analysis [8]. It is accepted that the second step is a complement of the first one [9] [10], in case that doctor has less confidence or even can't make decision only by inspecting skin surface. Skin biopsy image analysis can provide further information about the morbid condition that under the skin surface at in a microscopic vision [9] [11].…”

Section: Introductionmentioning

confidence: 99%

Multi-instance learning for skin biopsy image features recognition

Zhang

Shu

Liang

et al. 2012

2012 IEEE International Conference on Bioinformatics and Biomedicine

View full text Add to dashboard Cite

In this paper, a multi-instance learning framework is introduced to solve the problem of skin biopsy image features recognition. Previously reported methods for skin surface images were mostly based on color features extraction. They are incapable to be directly applied to skin biopsy image features recognition because biopsy images are often dyed and have obvious inner structures with different textures. Therefore, we regard skin biopsy images as multi-instance samples, whose instances are regions or structures captured by applying Normalized Cut. Texture feature extraction methods are used to express each region as a vectorial expression. Then two multi-instance learning algorithms reported successful in various image retrieval tasks were applied. Nine features were manually selected as target features to evaluate the proposed method on a skin disease diagnosis datasets of 6579 biopsy images from 2010 to 2011. The result showed that the proposed method is effective and medically acceptable.

show abstract

“…[4] In skin diseases that manifest with multiple lesions, once the physician performs complete physical examination of the patient along with a complete history he/she will choose the lesion to perform the biopsy. He/she will observe the most recent lesions, the most representative ones, in which no treatment was done, medically indicated or not, and if it is an evidence of more than one type of elementary lesion, he/she will decide to make as number of biopsies as types of lesions are present.…”

Section: Introductionmentioning

confidence: 99%